Awesome
3D-Reconstruction-with-Deep-Learning-Methods
The focus of this list is on open-source projects hosted on Github.
Projects released on Github
| TITLE | KEYWORDS | URL | LICENSE | Awesomeness |
|---|---|---|---|---|
| High Quality Monocular Depth Estimation via Transfer Learning | TensorFlow, PyTorch | https://github.com/ialhashim/DenseDepth https://arxiv.org/abs/1812.11941 | GPL-3.0 | |
| Multi-view stereo image-based 3D reconstruction | https://github.com/adahbingee/pais-mvs | nn | ||
| Hybrid Ensemble Approach For 3D Object Reconstruction from Multi-View Monocular RGB images | https://github.com/Ajithbalakrishnan/3D-Object-Reconstruction-from-Multi-View-Monocular-RGB-images | nn | ||
| Deep 3D Semantic Scene Extrapolation | hybrid CNN, GAN, TensorFlow | https://github.com/AliAbbasi/Deep-3D-Semantic-Scene-Extrapolation http://user.ceng.metu.edu.tr/~ys/pubs/extrap-tvcj18.pdf | nn | |
| ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans | TensorFlow | https://github.com/angeladai/ScanComplete | Apache-2.0 | |
| AtLoc: Attention Guided Camera Localization | PyTorch | https://github.com/BingCS/AtLoc https://arxiv.org/abs/1909.03557 | BY-NC-SA 4.0 | |
| PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation | TensorFlow, cuDNN | https://github.com/charlesq34/pointnet | MIT License | |
| PyTorch Implementation of DeepVO | PyTorch, CNN | https://github.com/ChiWeiHsiao/DeepVO-pytorch | nn | |
| Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence. | PyTorch | https://github.com/chrischoy/FCGF | MIT License | |
| Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020) | PyTorch | https://github.com/Colin97/MSN-Point-Cloud-Completion | Apache-2.0 | |
| Real-Time Self-Adaptive Deep Stereo | TensorFlow | https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo | Apache-2.0 | |
| Geometry meets semantics for semi-supervised monocular depth estimation - ACCV 2018 | TensorFlow | https://github.com/CVLAB-Unibo/Semantic-Mono-Depth | MIT License | |
| BlenderProc: A procedural blender pipeline to generate images for deep learning | Blender | https://github.com/DLR-RM/BlenderProc | GPL-3.0 | |
| SingleViewReconstruction: 3D Scene Reconstruction from a Single Viewport | TensorFlow | https://github.com/DLR-RM/SingleViewReconstruction | MIT License | |
| NNCAP — Neural Network Complex Approach to Photogrammetry | https://github.com/Dok11/nn-dldm | nn | ||
| Pytorch Implementation of Deeper Depth Prediction with Fully Convolutional Residual Networks | PyTorch | https://github.com/dontLoveBugs/FCRN_pytorch | nn | |
| Improved Adversarial Systems for 3D Object Generation and Reconstruction | GAN | https://github.com/EdwardSmith1884/3D-IWGAN | MIT License | |
| Deep Learning for Visual-Inertial Odometry | PyTorch, CNN | https://github.com/ElliotHYLee/Deep_Visual_Inertial_Odometry | MIT License | |
| Machine Vision | List | https://github.com/Ewenwan/MVision | nn | |
| Mesh R-CNN, an academic publication, presented at ICCV 2019 | PyTorch, R-CNN | https://github.com/facebookresearch/meshrcnn | BSD-3-Clause License | |
| PyTorch3d is FAIR's library of reusable components for deep learning with 3D data. | PyTorch | https://github.com/facebookresearch/pytorch3d | BSD-3-Clause License | |
| Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera | PyTorch | https://github.com/fangchangma/self-supervised-depth-completion | MIT License | |
| Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image | PyTorch | https://github.com/fangchangma/sparse-to-dense | BSD License | |
| Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image | PyTorch | https://github.com/fangchangma/sparse-to-dense.pytorch | nn | |
| PackNet-SfM: 3D Packing for Self-Supervised Monocular Depth Estimation | PyTorch | https://github.com/FangGet/PackNet-SFM-PyTorch | GPL-3.0 | |
| InvSFM: Revealing Scenes by Inverting Structure from Motion Reconstructions [CVPR 2019] | TensorFlow | https://github.com/francescopittaluga/invsfm | MIT License | |
| Deep Monocular Visual Odometry using PyTorch (Experimental) | PyTorch | https://github.com/fshamshirdar/DeepVO | nn | |
| PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation | PyTorch | https://github.com/fxia22/pointnet.pytorch | MIT License | |
| Pix2Depth - Depth Map Estimation from Monocular Image | Keras | https://github.com/gautam678/Pix2Depth | GPL-3.0 | |
| 3DRegNet: A Deep Neural Network for 3D Point Registration | TensorFlow | https://github.com/goncalo120/3DRegNet | MIT License | |
| Neural 3D Mesh Renderer – Single-Image 3D Reconstruction using Neural Renderer | https://github.com/hiroharu-kato/mesh_reconstruction | MIT License | ||
| Real-time Scalable Dense Surfel Mapping | https://github.com/HKUST-Aerial-Robotics/DenseSurfelMapping | nn | ||
| MVDepthNet: real-time multiview depth estimation neural network | PyTorch | https://github.com/HKUST-Aerial-Robotics/MVDepthNet | nn | |
| DeepMatchVO: Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation | https://github.com/hlzz/DeepMatchVO | MIT License | ||
| MIRorR: Matchable Image Retrieval by Learning from Surface Reconstruction | TensorFlow, CNN | https://github.com/hlzz/mirror | MIT License | |
| Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction | Caffe | https://github.com/Huangying-Zhan/Depth-VO-Feat | non-commercial | |
| Deep Learning 3D vision papers | papers, list, CN | https://github.com/huayong/dl-vision-papers | nn | |
| Open3D PointNet implementation with PyTorch | PyTorch, jupyter, Open3D | https://github.com/intel-isl/Open3D-PointNet | MIT License | |
| Semantic-TSDF for Self-driving Static Scene Reconstruction | PyTorch | https://github.com/irsisyphus/semantic-tsdf | MIT License | |
| Weakly supervised 3D Reconstruction with Adversarial Constraint | https://github.com/jgwak/McRecon | MIT License | ||
| Using Deep learning Technique for Stereo vision and 3D reconstruction | TensorFlow, CN | https://github.com/jiafeng5513/EvisionNet | nn | |
| Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video | PyTorch | https://github.com/JiawangBian/SC-SfMLearner-Release | GPL-3.0 | |
| Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries (official implementation) | PyTorch | https://github.com/JunjH/Revisiting_Single_Depth_Estimation | nn | |
| Visualization of Convolutional Neural Networks for Monocular Depth Estimation (official implementation) | CNN, PyTorch | https://github.com/JunjH/Visualizing-CNNs-for-monocular-depth-estimation | MIT License | |
| DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks | PyTorch | https://github.com/krrish94/DeepVO | nn | |
| DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction | Tensorflow | https://github.com/laughtervv/DISN | nn | |
| DeepTAM: Deep Tracking and Mapping | https://github.com/lmb-freiburg/deeptam | GPL-3.0 | ||
| DeMoN: Depth and Motion Network | Tensorflow | https://github.com/lmb-freiburg/demon | GPL-3.0 | |
| PyTorch implementation of CloudWalk's recent work DenseBody | PyTorch | https://github.com/Lotayou/densebody_pytorch | GPL-3.0 | |
| Self-supervised learning for dense depth estimation in monocular endoscopy | Tensorflow, Torch | https://github.com/lppllppl920/EndoscopyDepthEstimation-Pytorch | non-commercial | |
| ContextDesc: Local Descriptor Augmentation with Cross-Modality Context | Tensorflow | https://github.com/lzx551402/contextdesc | nn | |
| GL3D (Geometric Learning with 3D Reconstruction): a large-scale database created for 3D reconstruction and geometry-related learning problems | https://github.com/lzx551402/GL3D | MIT License | ||
| Deeper Depth Prediction with Fully Convolutional Residual Networks (official implementation) | Tensorflow | https://github.com/MahmoudSelmy/DeeperDepthEstimation | nn | |
| Fine-Tuning Vgg16 For Depth Estimation | Tensorflow | https://github.com/MahmoudSelmy/DepthEstimationVGG | nn | |
| 3D reconstruction with neural networks using Tensorflow. See link for Video | https://github.com/micmelesse/3D-reconstruction-with-Neural-Networks | nn | ||
| Learning Depth from Monocular Videos using Direct Methods | PyTorch | https://github.com/MightyChaos/LKVOLearner | BSD-3-Clause | |
| PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition | Tensorflow | https://github.com/mikacuy/pointnetvlad | MIT License | |
| Attempting to estimate topography of a region from image data | https://github.com/nbelakovski/topography_neural_net | nn | ||
| DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs | Tensorflow | https://github.com/neycyanshi/DDRNet | MIT License | |
| Monocular depth estimation from a single image | PyTorch | https://github.com/nianticlabs/monodepth2 | Copyright © Niantic, Inc. 2018. Patent Pending - non-commercial use only | |
| 3D-RelNet: Joint Object and Relation Network for 3D prediction | Torch, jupyter | https://github.com/nileshkulkarni/relative3d | nn | |
| PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image | Torch, RCNN | https://github.com/NVlabs/planercnn | Copyright (c) 2018 NVIDIA Corp. All Rights Reserved. This work is licensed under the Creative Commons Attribution NonCommercial ShareAlike 4.0 License. | |
| OctoMap - An Efficient Probabilistic 3D Mapping Framework Based on Octrees. | https://github.com/OctoMap/octomap | University of Freiburg, Copyright (C) 2009-2014, octomap: New BSD License, octovis and related libraries: GPL | ||
| Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch (Unofficial implementation) | PyTorch | https://github.com/OniroAI/MonoDepth-PyTorch | nn | |
| Learning to Sample: A learned sampling approach for point clouds | https://github.com/orendv/learning_to_sample | MIT License | ||
| DeepMVS: Learning Multi-View Stereopsis | CNN, PyTorch | https://github.com/phuang17/DeepMVS | BSD 2-clause | |
| DeepV2D: Video to Depth with Differentiable Structure from Motion | Tensorflow | https://github.com/princeton-vl/DeepV2D | nn | |
| High Quality Monocular Depth Estimation via Transfer Learning | Tensorflow | https://github.com/priya-dwivedi/Deep-Learning/tree/master/depth_estimation | nn (GPL-3.0 ?) | |
| Deep Single-View 3D Object Reconstruction with Visual Hull Embedding | CNN, Tensorflow | https://github.com/qweas120/PSVH-3d-reconstruction | MIT License | |
| ScanNet is an RGB-D video dataset containing 2.5 million views in more than 1500 scans, annotated with 3D camera poses,... | https://github.com/ScanNet/ScanNet | Can be used with the restriction to give credit and include original Copyright | ||
| Visual inspection of bridges is customarily used to identify and evaluate faults | CNN | https://github.com/Shaggyshak/CS543_project_Image-based-Localization-of-Bridge-Defects-with-AR-Visualization | nn | |
| Semantic 3D Occupancy Mapping through Efficient High Order CRFs | CNN | https://github.com/shichaoy/semantic_3d_mapping | BSD-3-Clause | |
| Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene | https://github.com/shubhtuls/factored3d | nn | ||
| Motion R-CNN codebase (old) | RCNN | https://github.com/simonmeister/old-motion-rcnn | MIT License | |
| Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation | PyTorch | https://github.com/sshan-zhao/GASDA | nn | |
| 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera | https://github.com/StanfordVL/3DSceneGraph | MIT License | ||
| Minkowski Engine is an auto-diff convolutional neural network library for high-dimensional sparse tensors | PyTorch | https://github.com/stanfordvl/MinkowskiEngine | MIT License | |
| Learning Single-View 3D Reconstruction with Limited Pose Supervision (Official implementation) | Tensorflow | https://github.com/stevenygd/3d-recon | MIT License | |
| VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera (Tensorflow version) | Tensorflow | https://github.com/timctho/VNect-tensorflow | Apache-2.0 | |
| 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image | https://github.com/val-iisc/3d-lmnet | MIT License | ||
| Learning to Find Good Correspondences | https://github.com/vcg-uvic/learned-correspondence-release | For reserch and evaluation only. Commercial usage requires written approval | ||
| A Framework for the Volumetric Integration of Depth Images | https://github.com/victorprad/InfiniTAM | non-commercial | ||
| Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation | Tensorflow | https://github.com/walsvid/Pixel2MeshPlusPlus | BSD-3-Clause | |
| Adversarial Semantic Scene Completion from a Single Depth Image (Official implementation) | Tensorflow | https://github.com/wangyida/gan-depth-semantic3d | nn | |
| SurfelWarp: Efficient Non-Volumetric Dynamic Reconstruction | https://github.com/weigao95/surfelwarp | BSD-3-Clause | ||
| PCN: Point Completion Network | Tensorflow | https://github.com/wentaoyuan/pcn | MIT License | |
| DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction | https://github.com/Xharlie/DISN | nn | ||
| Real-time motion from structure | CNN | https://github.com/yan99033/CNN-SVO | nn | |
| Dense 3D Object Reconstruction from a Single Depth View | Tensorflow | https://github.com/Yang7879/3D-RecGAN-extended | MIT License | |
| Semi-supervised monocular depth map prediction | Tensorflow | https://github.com/Yevkuzn/semodepth | GPL-3.0 | |
| 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration | Tensorflow | https://github.com/yewzijian/3DFeatNet | MIT License | |
| Estimated Depth Map Helps Image Classification: Depth estimation with neural network, and learning on RGBD images | https://github.com/yihui-he/Estimated-Depth-Map-Helps-Image-Classification | MIT License | ||
| Fit 3DMM to front and side face images simultaneously. | https://github.com/Yinghao-Li/3DMM-fitting | nn | ||
| The Perfect Match: 3D Point Cloud Matching with Smoothed Densities | CNN, Tensorflow | https://github.com/zgojcic/3DSmoothNet | BSD-3-Clause | |
| NeurVPS: Neural Vanishing Point Scanning via Conic Convolution | Tenosorflow | https://github.com/zhou13/neurvps | MIT License | |
| LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image (Torch implementation) | Torch | https://github.com/zouchuhang/LayoutNet | MIT License | |
| NeRF: Neural Radiance Fields | https://github.com/bmild/nerf | MIT License | 10 | |
| Local Light Field Fusion at SIGGRAPH 2019 | https://github.com/fyusion/llff | GPL-3.0 | 10 | |
| neural-volumes-learning-dynamic-renderable-volumes-from-images | https://research.fb.com/publications/neural-volumes-learning-dynamic-renderable-volumes-from-images/<br/>https://github.com/facebookresearch/neuralvolumes | BY-NC 4.0 | ||
| Learning Less is More - 6D Camera Localization via 3D Surface Regression | https://github.com/vislearn/LessMore | BSD-3-Clause | ||
| Local features | https://github.com/vcg-uvic/lf-net-release | |||
| Pix2Vox | https://github.com/hzxie/Pix2Vox | |||
| PlanarReconstruction: Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding | pytorch | https://github.com/svip-lab/PlanarReconstruction | ||
| Depth estimation with deep Neural networks | https://medium.com/@omarbarakat1995/depth-estimation-with-deep-neural-networks-part-1-5fa6d2237d0d<br/>https://medium.com/datadriveninvestor/depth-estimation-with-deep-neural-networks-part-2-81ee374888eb<br/>https://github.com/MahmoudSelmy/DeeperDepthEstimation<br/>https://github.com/MahmoudSelmy/DepthEstimationVGG/blob/master/README.md | |||
| High Quality Monocular Depth Estimation via Transfer Learning | https://github.com/ialhashim/DenseDepth<br />https://arxiv.org/abs/1812.11941 | |||
| D3Feat | https://github.com/XuyangBai/D3Feat | |||
| Hierarchical Deep Stereo Matching on High Resolution Images | pytorch | https://github.com/gengshan-y/high-res-stereo | MIT | |
| Structure-Aware Residual Pyramid Network for Monocular Depth Estimation | pytorch | https://github.com/Xt-Chen/SARPN | nn | |
| Pytorch code to construct a 3D point cloud model from single RGB image. | pytorch | https://github.com/lkhphuc/pytorch-3d-point-cloud-generation | nn | |
| Depth estimation from RGB images using fully convolutional neural networks | pytorch | https://github.com/karoly-hars/DE_resnet_unet_hyb | BSD-3-Clause | |
| Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding | torch, tensorflow | https://github.com/svip-lab/PlanarReconstruction | MIT | |
| TriDepth: Triangular Patch-based Deep Depth Prediction | PyTorch | https://github.com/syinari0123/tridepth | MIT | |
| Depth Map Prediction from a Single Image using a Multi-Scale Deep Network | torch | https://github.com/imran3180/depth-map-prediction | nn | |
| Hybrid CNN for Single Image Depth Estimation | torch | https://github.com/karoly-hars/DE_resnet_unet_hyb | BSD-3-Clause | |
| MarrNet: 3D Shape Reconstruction via 2.5D Sketches | torch | https://github.com/jiajunwu/marrnet | nn | |
| Consistent Video Depth Estimation | https://roxanneluo.github.io/Consistent-Video-Depth-Estimation/ | nn | ||
| HF-Net: Robust Hierarchical Localization at Large Scale | torch, tensorflow | https://github.com/ethz-asl/hfnet | MIT | |
| Hierarchical Deep Stereo Matching on High Resolution Images | pytorch | https://github.com/gengshan-y/high-res-stereo | MIT | |
| Structure-Aware Residual Pyramid Network for Monocular Depth Estimation | pytorch | https://github.com/Xt-Chen/SARPN | nn | |
| Pytorch code to construct a 3D point cloud model from single RGB image. | pytorch | https://github.com/lkhphuc/pytorch-3d-point-cloud-generation | nn | |
| Depth estimation from RGB images using fully convolutional neural networks | pytorch | https://github.com/karoly-hars/DE_resnet_unet_hyb | BSD-3-Clause | |
| Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding | torch, tensorflow | https://github.com/svip-lab/PlanarReconstruction | MIT | |
| TriDepth: Triangular Patch-based Deep Depth Prediction | PyTorch | https://github.com/syinari0123/tridepth | MIT | |
| Depth Map Prediction from a Single Image using a Multi-Scale Deep Network | torch | https://github.com/imran3180/depth-map-prediction | nn | |
| Hybrid CNN for Single Image Depth Estimation | torch | https://github.com/karoly-hars/DE_resnet_unet_hyb | BSD-3-Clause | |
| MarrNet: 3D Shape Reconstruction via 2.5D Sketches | torch | https://github.com/jiajunwu/marrnet | nn | |
| Consistent Video Depth Estimation | https://roxanneluo.github.io/Consistent-Video-Depth-Estimation/ | nn | ||
| HF-Net: Robust Hierarchical Localization at Large Scale | torch, tensorflow | https://github.com/ethz-asl/hfnet | MIT |
Other Projects
| TITLE | KEYWORDS | URL | LICENSE |
|---|---|---|---|
| 3D-Scene-GAN: Three-dimensional Scene Reconstruction with Generative Adversarial Networks | paper | https://openreview.net/forum?id=SkNEsmJwf | |
| Google: Deep Learning Depth Prediction | magazine article, GER | https://www.digitalproduction.com/2019/05/27/google-deep-learning-depth-prediction/ | |
| SLAM and Deep Leraning for 3D Indoor Scene Understanding | PhD thesis | https://www.doc.ic.ac.uk/~ajd/Publications/McCormac-J-2019-PhD-Thesis.pdf | |
| Dense 3D Object Reconstruction from a Single Depth View | 3D-RecGAN++ | https://arxiv.org/abs/1802.00411 | |
| Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction | https://ai.googleblog.com/2019/05/moving-camera-moving-people-deep.html | ||
| Depth Estimation from a Single RGB Image | http://campar.in.tum.de/Chair/ProjectDepthPrediction | ||
| Deep Fundamental Matrix Estimation | http://vladlen.info/papers/deep-fundamental.pdf | ||
| depth_estimation | https://towardsdatascience.com/depth-estimation-on-camera-images-using-densenets-ac454caa893 | ||
| 3D-Machine-Learning List | https://github.com/timzhang642/3D-Machine-Learning | ||
| DEEP LEARNING-BASED 3D OBJECT RECONSTRUCTION - A SURVEY - Image-based 3D Object Reconstruction:State-of-the-Art and Trends in the DeepLearning Era | https://arxiv.org/pdf/1906.06543.pdf | ||
I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs (CVPR 2023) https://github.com/jingsenzhu/i2-sdf MIT
https://github.com/lioryariv/idr
https://github.com/autonomousvision/differentiable_volumetric_rendering
https://github.com/Dok11/surface-match-dataset
Image-based 3D Object Reconstruction:State-of-the-Art and Trends in the DeepLearning Era https://arxiv.org/pdf/1906.06543v3.pdf
Dense 3D Object Reconstructionfrom a Single Depth View https://arxiv.org/pdf/1802.00411v2.pdf
https://dagshub.com/OperationSavta/SavtaDepth https://colab.research.google.com/drive/1XU4DgQ217_hUMU1dllppeQNw3pTRlHy1?usp=sharing https://huggingface.co/spaces/kingabzpro/savtadepth MIT License
https://github.com/gradslam/gradslam pyTorch